Abstract: A method of managing information in a content-addressable computer system comprising a plurality of computers including at least a first computer and at least two second computers. The method includes creating a first identifier for a data item, at least in part, by hashing the content of the data item; sending a request including the first identifier from the first computer to the at least two second computers to access the data item, wherein at least one of the at least two second computers uses the first identifier to access the data item; and verifying that the content of the data item has not changed since the creation of the first identifier. 2. The method may include using the first identifier to locate a storage location for the data item on the computer system.

Abstract: A file system includes a plurality of servers to store file data as segments or chunks; and first data that includes file identifiers for files for which the file data are stored as segments; and second data that maps the file identifiers to the segments to which the file identifiers correspond; and location data that identifies which of the plurality of servers stores which of the segments, the location data being keyed on segment identifiers, each segment identifier being based on the data in a corresponding segment.

Abstract: A method, in a system in which a plurality of data items are distributed across a plurality of computers, includes, at a first computer in the network, (a) receiving from a requesting computer in said network, a request, the request including a specific name of a particular data item, wherein the particular data item comprises a particular sequence of bits, and wherein the specific name of the particular data item is based at least in part on the data comprising the particular data item, the specific name of the particular data item having been determined, at least in part, using a given function of the particular sequence of bits, wherein two identical sequences of bits have the same name as determined using the given function; and (b) causing said requesting computer to obtain at least a portion of said particular data item from a second computer in said network, said second computer being distinct from said first computer.

Abstract: In a data processing system, a method includes deleting a particular copy of a data item when at least one other copy of the data item is available. The presence of another copy of the data item is determined, at least in part, based on an identifier for the data item, the identifier having been computed using all of the data in the data item and only the data in the data item, wherein two identical data items in the data processing system will have identical identifiers. The particular copy of the data item may be deleted if another copy of the data is determined to be present on another processor in the system or on the same processor. The identifier of the data item is computed using a function such as a message digest or hash function which may be: MD4, MD5, or SHA.

Abstract: A method of distributing a data item to a plurality of computers in a network of computers. A data item is divided into a plurality of segments. Each segment is stored on at least one computer in said network. A list of computers onto which each of said segments has been stored is maintained. When a data item is requested, its component segments are obtained from at least two computers in the network. Some of the computers may form a peer-to-peer network.

Abstract: Similarity of data items is determined by analyzing corresponding segments of the data items. A function is applied to each segment of a data item and the output of that function is compared to the output of the same function applied to a corresponding segment of another data item. A function may be applied to the output of the functions. The functions may be hash or message digest functions.

Abstract: Access to and delivery of licensed content is controlled using content names that were determined based on the content. A name for a data item is obtained, the name having been determined based at least in part on the data which comprise the contents of the data item. Access to the data item is authorized based at least in part on the name. Once authorized, access may be granted from more than one computer. The name may have been determined using a hash or message digest function such as MD4, MD5 or SHA. The data item may comprise a file, a portion of a file, a page in memory, a digital message, a digital image, a video signal or an audio signal.

Abstract: A framework operative in a computer network in which users of client processors connect to a content server, wherein processors in the network communicate with each other using a TCP/IP communication protocol. The framework includes a set of content servers, distinct from the content provider server, for hosting at least some of the data files that are normally hosted by the content provider server. In response to requests for a data file, generated by one of the client machines, the particular data file is served from one of the content servers having been selected based at least in part on a measure of availability of at least one of the servers of the network of servers.

Abstract: A method of distributing a data item to a plurality of computers in a network of computers. A data item is divided into a plurality of segments. Each segment is stored on at least one computer in said network. A list of computers onto which each of said segments has been stored is maintained. When a data item is requested, its component segments are obtained from at least two computers in the network. Some of the computers may form a peer-to-peer network.

Abstract: Similarity of data items is determined by analyzing corresponding segments of the data items. A function is applied to each segment of a data item and the output of that function is compared to the output of the same function applied to a corresponding segment of another data item. A function may be applied to the output of the functions. The functions may be hash or message digest functions.

Abstract: Access to and delivery of licensed content is controlled using content names that were determined based on the content. A name for a data item is obtained, the name having been determined based at least in part on the data which comprise the contents of the data item. Access to the data item is authorized based at least in part on the name. Once authorized, access may be granted from more than one computer. The name may have been determined using a hash or message digest function such as MD4, MD5 or SHA. The data item may comprise a file, a portion of a file, a page in memory, a digital message, a digital image, a video signal or an audio signal.

Abstract: A plurality of data items are distributed across a plurality of computers, some of which may form a peer-to-peer network. A first computer receives a request for a data item from a requesting computer. The request includes a True Name of the data item. The first computer causes the requesting computer to obtain the data item from a second computer, distinct from the first computer. The first computer may not have a copy of the requested data item. The first computer may know the location of the data item. The first computer may forward the request for the data item to at least one other computer.

Abstract: Data files are distributed across a plurality of computers. The computers may form a network such as a content delivery network (CDN) or a peer-to-peer network. The network may operate as a TCP/IP network such as the Internet. Data files may represent may represent digital messages, images, videos or audio signals. For content—data items or files in the system—a name is obtained (or determined), where the name is based, at least in part, on a given function of the data in a data item or file. The given function may be a message digest or hash function, and it may be MD4, MD5, and SHA. A cony of a requested file is only provided to licensed (or authorized) parties. The system may check one or more computers for unauthorized or unlicensed content. Content is served based on a measure of availability of servers.

Abstract: In a data processing system, a mechanism identifies data items by substantially unique identifiers which depend on all of the data in the data items and only on the data in the data items. Existence means determine whether a particular data item is present in the system, by examining the identifiers of the plurality of data items.

Abstract: In a system in which a set of data items are distributed across a network of servers, at least some of the data items being cached versions of data items from a source server, a content delivery method includes determining a data identifier for a particular data item, the data identifier being determined using a given function of the data comprising the particular data item; and responsive to a request for the particular data item, the request including at least the data identifier of the particular data item, providing the particular data item from a given one of the servers of the network of servers. The request for the particular data item may be resolved based on a measure of availability of at least one of the servers, where the measure of availability may be a measurement of bandwidth to the server; a measurement of a cost of a connection to the server, and/or a measurement of a reliability of a connection to the server.

Abstract: In a data processing system, a mechanism identifies data items by substantially unique identifiers which depend on all of the data in the data items and only on the data in the data items. Existence means determine whether a particular data item is present in the system, by examining the identifiers of the plurality of data items.

Abstract: In a data processing system, a mechanism identifies data items by substantially unique identifiers which depend on all of the data in the data items and only on the data in the data items. The system also determines whether a particular data item is present in the database by examining the identifiers of the plurality of data items.